I am comparing 5 methods to analyze body fat mass, and I need look at the concordance. Can anyone explain how to make Lin's concordance and ROC curve in SPPS, or in other software?
Hello Dr Mielgo-Ayuso, I have not used SPSS to create an ROC curve, but years ago I did use meta-test to do this I think the program was from memory although my memory seems a bit bad at present so maybe I just need to find this to check and If you want me to find the abstract I think I can do this. Thanks Debbie
Hello Juan, you are testing my memory, but it is not as bad as I had thought in that I've found my sheet of analysis from about 10 years ago that relates to LVH and cardiovascular events where I tried to do this ROC curve. I am not an expert, and this program I have just tried to run/ open does not work now as it is DOS based and basic. I should delete all the rubbish from my computer really as a lot of it is now obsolete, but just time is a factor. All the best with your work, Regards, Deborah
ps. I can send the basic sheet of analysis and the abstract if you require this [is your email on your website?]
Meta-Test version 0.6 April 30, 1997
Copyright 1992-1997 Joseph Lau, MD
This is the first "beta" release version of Meta-Test, a program to conduct
statistical analysis of diagnostic test data. This program shares similar
interface and file format as the Meta-Analyst family of meta-analysis software.
This program is written in Turbo Pascal version 5.5/7.0 and runs under DOS.
Hello Juan, I just tried to send you basic analysis and ROC curve that I did on heart hypertrophy. Message below was given when I used this email. I hope you are able to find a program whereby you can do your analysis. Regards, Debbie
Delivery to the following recipient failed permanently:
Google tried to deliver your message, but it was rejected by the recipient domain. We recommend contacting the other email provider for further information about the cause of this error. The error that the other server returned was: 550 550 sorry, no mailbox here by that name. (#5.7.17)
I think it is more easier to do it in the Medcalc, It could be done for each of the studied methods separately, as well as the combined ROC curve.
you minimally need two sets of data - one categorical (depending on the studied criteria- as being diabetic or not) and other variations in glucose concentrations (same model basically goes for other situations).